text2spoken 0.0.2a1__tar.gz

text2spoken-0.0.2a1/LICENSE

@@ -0,0 +1,202 @@
+
+                                 Apache License
+                           Version 2.0, January 2004
+                        http://www.apache.org/licenses/
+
+   TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
+
+   1. Definitions.
+
+      "License" shall mean the terms and conditions for use, reproduction,
+      and distribution as defined by Sections 1 through 9 of this document.
+
+      "Licensor" shall mean the copyright owner or entity authorized by
+      the copyright owner that is granting the License.
+
+      "Legal Entity" shall mean the union of the acting entity and all
+      other entities that control, are controlled by, or are under common
+      control with that entity. For the purposes of this definition,
+      "control" means (i) the power, direct or indirect, to cause the
+      direction or management of such entity, whether by contract or
+      otherwise, or (ii) ownership of fifty percent (50%) or more of the
+      outstanding shares, or (iii) beneficial ownership of such entity.
+
+      "You" (or "Your") shall mean an individual or Legal Entity
+      exercising permissions granted by this License.
+
+      "Source" form shall mean the preferred form for making modifications,
+      including but not limited to software source code, documentation
+      source, and configuration files.
+
+      "Object" form shall mean any form resulting from mechanical
+      transformation or translation of a Source form, including but
+      not limited to compiled object code, generated documentation,
+      and conversions to other media types.
+
+      "Work" shall mean the work of authorship, whether in Source or
+      Object form, made available under the License, as indicated by a
+      copyright notice that is included in or attached to the work
+      (an example is provided in the Appendix below).
+
+      "Derivative Works" shall mean any work, whether in Source or Object
+      form, that is based on (or derived from) the Work and for which the
+      editorial revisions, annotations, elaborations, or other modifications
+      represent, as a whole, an original work of authorship. For the purposes
+      of this License, Derivative Works shall not include works that remain
+      separable from, or merely link (or bind by name) to the interfaces of,
+      the Work and Derivative Works thereof.
+
+      "Contribution" shall mean any work of authorship, including
+      the original version of the Work and any modifications or additions
+      to that Work or Derivative Works thereof, that is intentionally
+      submitted to Licensor for inclusion in the Work by the copyright owner
+      or by an individual or Legal Entity authorized to submit on behalf of
+      the copyright owner. For the purposes of this definition, "submitted"
+      means any form of electronic, verbal, or written communication sent
+      to the Licensor or its representatives, including but not limited to
+      communication on electronic mailing lists, source code control systems,
+      and issue tracking systems that are managed by, or on behalf of, the
+      Licensor for the purpose of discussing and improving the Work, but
+      excluding communication that is conspicuously marked or otherwise
+      designated in writing by the copyright owner as "Not a Contribution."
+
+      "Contributor" shall mean Licensor and any individual or Legal Entity
+      on behalf of whom a Contribution has been received by Licensor and
+      subsequently incorporated within the Work.
+
+   2. Grant of Copyright License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      copyright license to reproduce, prepare Derivative Works of,
+      publicly display, publicly perform, sublicense, and distribute the
+      Work and such Derivative Works in Source or Object form.
+
+   3. Grant of Patent License. Subject to the terms and conditions of
+      this License, each Contributor hereby grants to You a perpetual,
+      worldwide, non-exclusive, no-charge, royalty-free, irrevocable
+      (except as stated in this section) patent license to make, have made,
+      use, offer to sell, sell, import, and otherwise transfer the Work,
+      where such license applies only to those patent claims licensable
+      by such Contributor that are necessarily infringed by their
+      Contribution(s) alone or by combination of their Contribution(s)
+      with the Work to which such Contribution(s) was submitted. If You
+      institute patent litigation against any entity (including a
+      cross-claim or counterclaim in a lawsuit) alleging that the Work
+      or a Contribution incorporated within the Work constitutes direct
+      or contributory patent infringement, then any patent licenses
+      granted to You under this License for that Work shall terminate
+      as of the date such litigation is filed.
+
+   4. Redistribution. You may reproduce and distribute copies of the
+      Work or Derivative Works thereof in any medium, with or without
+      modifications, and in Source or Object form, provided that You
+      meet the following conditions:
+
+      (a) You must give any other recipients of the Work or
+          Derivative Works a copy of this License; and
+
+      (b) You must cause any modified files to carry prominent notices
+          stating that You changed the files; and
+
+      (c) You must retain, in the Source form of any Derivative Works
+          that You distribute, all copyright, patent, trademark, and
+          attribution notices from the Source form of the Work,
+          excluding those notices that do not pertain to any part of
+          the Derivative Works; and
+
+      (d) If the Work includes a "NOTICE" text file as part of its
+          distribution, then any Derivative Works that You distribute must
+          include a readable copy of the attribution notices contained
+          within such NOTICE file, excluding those notices that do not
+          pertain to any part of the Derivative Works, in at least one
+          of the following places: within a NOTICE text file distributed
+          as part of the Derivative Works; within the Source form or
+          documentation, if provided along with the Derivative Works; or,
+          within a display generated by the Derivative Works, if and
+          wherever such third-party notices normally appear. The contents
+          of the NOTICE file are for informational purposes only and
+          do not modify the License. You may add Your own attribution
+          notices within Derivative Works that You distribute, alongside
+          or as an addendum to the NOTICE text from the Work, provided
+          that such additional attribution notices cannot be construed
+          as modifying the License.
+
+      You may add Your own copyright statement to Your modifications and
+      may provide additional or different license terms and conditions
+      for use, reproduction, or distribution of Your modifications, or
+      for any such Derivative Works as a whole, provided Your use,
+      reproduction, and distribution of the Work otherwise complies with
+      the conditions stated in this License.
+
+   5. Submission of Contributions. Unless You explicitly state otherwise,
+      any Contribution intentionally submitted for inclusion in the Work
+      by You to the Licensor shall be under the terms and conditions of
+      this License, without any additional terms or conditions.
+      Notwithstanding the above, nothing herein shall supersede or modify
+      the terms of any separate license agreement you may have executed
+      with Licensor regarding such Contributions.
+
+   6. Trademarks. This License does not grant permission to use the trade
+      names, trademarks, service marks, or product names of the Licensor,
+      except as required for reasonable and customary use in describing the
+      origin of the Work and reproducing the content of the NOTICE file.
+
+   7. Disclaimer of Warranty. Unless required by applicable law or
+      agreed to in writing, Licensor provides the Work (and each
+      Contributor provides its Contributions) on an "AS IS" BASIS,
+      WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
+      implied, including, without limitation, any warranties or conditions
+      of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
+      PARTICULAR PURPOSE. You are solely responsible for determining the
+      appropriateness of using or redistributing the Work and assume any
+      risks associated with Your exercise of permissions under this License.
+
+   8. Limitation of Liability. In no event and under no legal theory,
+      whether in tort (including negligence), contract, or otherwise,
+      unless required by applicable law (such as deliberate and grossly
+      negligent acts) or agreed to in writing, shall any Contributor be
+      liable to You for damages, including any direct, indirect, special,
+      incidental, or consequential damages of any character arising as a
+      result of this License or out of the use or inability to use the
+      Work (including but not limited to damages for loss of goodwill,
+      work stoppage, computer failure or malfunction, or any and all
+      other commercial damages or losses), even if such Contributor
+      has been advised of the possibility of such damages.
+
+   9. Accepting Warranty or Additional Liability. While redistributing
+      the Work or Derivative Works thereof, You may choose to offer,
+      and charge a fee for, acceptance of support, warranty, indemnity,
+      or other liability obligations and/or rights consistent with this
+      License. However, in accepting such obligations, You may act only
+      on Your own behalf and on Your sole responsibility, not on behalf
+      of any other Contributor, and only if You agree to indemnify,
+      defend, and hold each Contributor harmless for any liability
+      incurred by, or claims asserted against, such Contributor by reason
+      of your accepting any such warranty or additional liability.
+
+   END OF TERMS AND CONDITIONS
+
+   APPENDIX: How to apply the Apache License to your work.
+
+      To apply the Apache License to your work, attach the following
+      boilerplate notice, with the fields enclosed by brackets "[]"
+      replaced with your own identifying information. (Don't include
+      the brackets!)  The text should be enclosed in the appropriate
+      comment syntax for the file format. We also recommend that a
+      file or class name and description of purpose be included on the
+      same "printed page" as the copyright notice for easier
+      identification within third-party archives.
+
+   Copyright 2026 TigreGotico Lda
+
+   Licensed under the Apache License, Version 2.0 (the "License");
+   you may not use this file except in compliance with the License.
+   You may obtain a copy of the License at
+
+       http://www.apache.org/licenses/LICENSE-2.0
+
+   Unless required by applicable law or agreed to in writing, software
+   distributed under the License is distributed on an "AS IS" BASIS,
+   WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+   See the License for the specific language governing permissions and
+   limitations under the License.

text2spoken-0.0.2a1/PKG-INFO

@@ -0,0 +1,100 @@
+Metadata-Version: 2.4
+Name: text2spoken
+Version: 0.0.2a1
+Summary: Rewrite written text into the words a voice speaks: numbers, dates, times, units, titles and contractions
+Author-email: JarbasAI <jarbasai@mailfence.com>
+License: Apache-2.0
+Project-URL: Homepage, https://github.com/TigreGotico/text2spoken
+Classifier: Programming Language :: Python :: 3
+Classifier: License :: OSI Approved :: Apache Software License
+Classifier: Operating System :: OS Independent
+Classifier: Topic :: Text Processing :: Linguistic
+Requires-Python: >=3.11
+Description-Content-Type: text/markdown
+License-File: LICENSE
+Requires-Dist: ovos-number-parser>=0.4.0
+Requires-Dist: ovos-date-parser>=0.6.4a1
+Requires-Dist: unicode_rbnf>=2.0.0
+Provides-Extra: test
+Requires-Dist: pytest; extra == "test"
+Dynamic: license-file
+
+# text2spoken
+
+text2spoken rewrites written text into the words a voice speaks. It expands numbers, dates, times, units, titles and contractions. A phonemizer then reads words, not digits or symbols.
+
+## Quickstart
+
+```bash
+pip install --pre text2spoken
+```
+
+```python
+from text2spoken import normalize
+
+print(normalize("Dr. Smith paid 3/4 of the bill at 25°C.", "en"))
+print(normalize("O Sr. Silva pagou 10kg às 14h30.", "pt-PT"))
+```
+
+```text
+Doctor Smith paid three quarters of the bill at twenty five degrees celsius.
+O Senhor Silva pagou dez quilogramas às catorze e trinta.
+```
+
+## Where this fits
+
+Alone: it turns written text into spoken words, with `from text2spoken import normalize`.
+In the stack: it is the normalisation stage. A frontend or a TTS library calls it before phonemization, and it calls `ovos-number-parser`, `ovos-date-parser` and `unicode_rbnf`.
+Through scriptconv: scriptconv has no `normalize` extra. Install `text2spoken` directly.
+
+## What `normalize` does
+
+`normalize(text, lang)` runs four passes in this order:
+
+1. It expands dates and times, such as `03/08/2025` and `14h30`.
+2. It splits a word from a digit that a hyphen joins, such as `sub-23`. A range such as `3-2` stays as it is.
+3. It expands units and ordinal indicators, such as `10kg`, `25°C` and `1º`.
+4. It reads each word, and expands contractions, titles, fractions and numbers.
+
+Each pass is also a plain function, so a frontend can compose them and add its own rules. See [docs/api.md](docs/api.md).
+
+The language tag selects the rules. The tables use the part before the first hyphen, so `pt-BR` and `pt-PT` share one table. `en-US` reads an ambiguous date as month first, and every other tag reads it as day first.
+
+## Languages
+
+These languages have tables in `text2spoken/tables.py`:
+
+| Table | Languages |
+| --- | --- |
+| `CONTRACTIONS` | en |
+| `TITLES` | ca, de, en, es, fr, gl, it, nl, pt |
+| `UNITS` | de, en, es, fr, pt |
+
+This command prints the same list from the installed package:
+
+```bash
+python -c "from text2spoken import CONTRACTIONS, TITLES, UNITS; [print(sorted(t)) for t in (CONTRACTIONS, TITLES, UNITS)]"
+```
+
+Numbers, dates and times come from `ovos-number-parser` and `ovos-date-parser`, so those packages set their language coverage.
+
+To add a language, add its entries to `text2spoken/tables.py`. A new language needs no code change.
+
+## Behaviour to know
+
+- The library uses no network and loads no model, so it works offline.
+- A language that the parsers do not support keeps its digits. The library logs an error and returns the text.
+- A `text` or `lang` value of the wrong type raises `TypeError` or `AttributeError` from the code that reads it.
+- Importing the library imports `ovos-date-parser`, which sets the import time.
+- `ovos-config`, a dependency of `ovos-date-parser`, creates `~/.config/mycroft` at import.
+
+## Development
+
+```bash
+uv pip install --prerelease=allow -e ".[test]"
+pytest tests
+```
+
+## Licence
+
+Apache-2.0. See [LICENSE](LICENSE).

text2spoken-0.0.2a1/README.md

@@ -0,0 +1,79 @@
+# text2spoken
+
+text2spoken rewrites written text into the words a voice speaks. It expands numbers, dates, times, units, titles and contractions. A phonemizer then reads words, not digits or symbols.
+
+## Quickstart
+
+```bash
+pip install --pre text2spoken
+```
+
+```python
+from text2spoken import normalize
+
+print(normalize("Dr. Smith paid 3/4 of the bill at 25°C.", "en"))
+print(normalize("O Sr. Silva pagou 10kg às 14h30.", "pt-PT"))
+```
+
+```text
+Doctor Smith paid three quarters of the bill at twenty five degrees celsius.
+O Senhor Silva pagou dez quilogramas às catorze e trinta.
+```
+
+## Where this fits
+
+Alone: it turns written text into spoken words, with `from text2spoken import normalize`.
+In the stack: it is the normalisation stage. A frontend or a TTS library calls it before phonemization, and it calls `ovos-number-parser`, `ovos-date-parser` and `unicode_rbnf`.
+Through scriptconv: scriptconv has no `normalize` extra. Install `text2spoken` directly.
+
+## What `normalize` does
+
+`normalize(text, lang)` runs four passes in this order:
+
+1. It expands dates and times, such as `03/08/2025` and `14h30`.
+2. It splits a word from a digit that a hyphen joins, such as `sub-23`. A range such as `3-2` stays as it is.
+3. It expands units and ordinal indicators, such as `10kg`, `25°C` and `1º`.
+4. It reads each word, and expands contractions, titles, fractions and numbers.
+
+Each pass is also a plain function, so a frontend can compose them and add its own rules. See [docs/api.md](docs/api.md).
+
+The language tag selects the rules. The tables use the part before the first hyphen, so `pt-BR` and `pt-PT` share one table. `en-US` reads an ambiguous date as month first, and every other tag reads it as day first.
+
+## Languages
+
+These languages have tables in `text2spoken/tables.py`:
+
+| Table | Languages |
+| --- | --- |
+| `CONTRACTIONS` | en |
+| `TITLES` | ca, de, en, es, fr, gl, it, nl, pt |
+| `UNITS` | de, en, es, fr, pt |
+
+This command prints the same list from the installed package:
+
+```bash
+python -c "from text2spoken import CONTRACTIONS, TITLES, UNITS; [print(sorted(t)) for t in (CONTRACTIONS, TITLES, UNITS)]"
+```
+
+Numbers, dates and times come from `ovos-number-parser` and `ovos-date-parser`, so those packages set their language coverage.
+
+To add a language, add its entries to `text2spoken/tables.py`. A new language needs no code change.
+
+## Behaviour to know
+
+- The library uses no network and loads no model, so it works offline.
+- A language that the parsers do not support keeps its digits. The library logs an error and returns the text.
+- A `text` or `lang` value of the wrong type raises `TypeError` or `AttributeError` from the code that reads it.
+- Importing the library imports `ovos-date-parser`, which sets the import time.
+- `ovos-config`, a dependency of `ovos-date-parser`, creates `~/.config/mycroft` at import.
+
+## Development
+
+```bash
+uv pip install --prerelease=allow -e ".[test]"
+pytest tests
+```
+
+## Licence
+
+Apache-2.0. See [LICENSE](LICENSE).

text2spoken-0.0.2a1/pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools>=68", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "text2spoken"
+dynamic = ["version"]
+description = "Rewrite written text into the words a voice speaks: numbers, dates, times, units, titles and contractions"
+license = {text = "Apache-2.0"}
+classifiers = [
+    "Programming Language :: Python :: 3",
+    "License :: OSI Approved :: Apache Software License",
+    "Operating System :: OS Independent",
+    "Topic :: Text Processing :: Linguistic",
+]
+authors = [{name = "JarbasAI", email = "jarbasai@mailfence.com"}]
+readme = "README.md"
+requires-python = ">=3.11"
+dependencies = [
+    "ovos-number-parser>=0.4.0",
+    "ovos-date-parser>=0.6.4a1",
+    "unicode_rbnf>=2.0.0",
+]
+
+[project.urls]
+Homepage = "https://github.com/TigreGotico/text2spoken"
+
+[project.optional-dependencies]
+test = [
+    "pytest",
+]
+
+[tool.setuptools.dynamic]
+version = {attr = "text2spoken.version.__version__"}
+
+[tool.setuptools.packages.find]
+where = ["."]
+include = ["text2spoken*"]

text2spoken-0.0.2a1/setup.cfg

@@ -0,0 +1,4 @@
+[egg_info]
+tag_build = 
+tag_date = 0
+

text2spoken-0.0.2a1/tests/test_normalization_package.py

@@ -0,0 +1,93 @@
+import logging
+import unittest
+
+import text2spoken as normalization
+from text2spoken import datetimes, numbers, tables, text
+from text2spoken import units as units_module
+
+# Every name the package exports from its modules, with the module that owns it.
+MOVED_NAMES = {
+    "CONTRACTIONS": tables, "TITLES": tables, "UNITS": tables,
+    "normalize": text, "is_fraction": numbers,
+    "pronounce_date": datetimes, "pronounce_time": datetimes,
+    "_get_number_separators": numbers, "_normalize_number_word": numbers,
+    "_normalize_dates_and_times": datetimes, "_normalize_word_hyphen_digit": text,
+    "_normalize_units": units_module, "_normalize_word": text,
+}
+
+
+class TestPackageExports(unittest.TestCase):
+
+    def test_every_moved_name_is_importable_from_the_package(self):
+        for name, owner in MOVED_NAMES.items():
+            with self.subTest(name=name):
+                self.assertIs(getattr(normalization, name), getattr(owner, name))
+
+    def test_each_module_logs_to_the_library_logger(self):
+        for module in (datetimes, numbers, text, units_module):
+            with self.subTest(module=module.__name__):
+                self.assertIs(module.LOG, logging.getLogger("text2spoken"))
+
+    def test_lang_identity_helpers_stay_outside_the_library(self):
+        for name in ("normalize_lang", "match_lang"):
+            with self.subTest(name=name):
+                self.assertFalse(hasattr(normalization, name))
+
+
+class TestPackageLayout(unittest.TestCase):
+    """Tables are data, apart from the code that applies them."""
+
+    def test_tables_module_holds_only_data(self):
+        self.assertEqual(
+            {"CONTRACTIONS", "TITLES", "UNITS"},
+            {n for n in vars(tables) if not n.startswith("__")},
+        )
+
+    def test_each_concern_owns_its_transformations(self):
+        self.assertTrue(hasattr(numbers, "_normalize_number_word"))
+        self.assertTrue(hasattr(datetimes, "_normalize_dates_and_times"))
+        self.assertTrue(hasattr(units_module, "_normalize_units"))
+        self.assertTrue(hasattr(text, "normalize"))
+
+
+class TestPipelineStillNormalizes(unittest.TestCase):
+    """A spot check on the whole pipeline, independent of the unit tests."""
+
+    def test_english_sentence_leaves_no_digits_or_symbols(self):
+        out = normalization.normalize("Dr. Smith owes me 12.5% of 3/4 at 25°C", "en")
+        self.assertFalse(any(c.isdigit() for c in out), out)
+        self.assertIn("Doctor", out)
+        self.assertIn("per cent", out)
+        self.assertIn("degrees celsius", out)
+
+    def test_portuguese_uses_the_portuguese_tables(self):
+        out = normalization.normalize("Sr. Silva pagou 10kg", "pt")
+        self.assertIn("Senhor", out)
+        self.assertIn("quilogramas", out)
+
+    def test_digit_hyphen_digit_score_is_left_intact_pt(self):
+        # A score is a range, not a word glued to a digit: the phonemizer,
+        # not this pipeline, is responsible for reading "3-2" aloud.
+        out = normalization.normalize("O jogo é 3-2.", "pt-PT")
+        self.assertEqual(out, "O jogo é 3-2.")
+
+    def test_digit_hyphen_digit_score_is_left_intact_en(self):
+        out = normalization.normalize("The score is 3-2.", "en-US")
+        self.assertEqual(out, "The score is 3-2.")
+
+    def test_digit_hyphen_digit_page_range_is_left_intact(self):
+        out = normalization.normalize("páginas 1139-1185", "pt-PT")
+        self.assertEqual(out, "páginas 1139-1185")
+
+    def test_digit_en_dash_digit_range_is_left_intact(self):
+        out = normalization.normalize("páginas 1139–1185", "pt-PT")
+        self.assertEqual(out, "páginas 1139–1185")
+
+    def test_word_hyphen_digit_still_normalizes(self):
+        out = normalization.normalize("sub-23", "en-US")
+        self.assertNotIn("-", out)
+        self.assertIn("twenty", out.lower())
+
+
+if __name__ == "__main__":
+    unittest.main()

text2spoken-0.0.2a1/tests/test_normalize_dates_times.py

@@ -0,0 +1,110 @@
+import unittest
+
+from text2spoken import _normalize_dates_and_times
+
+
+class TestAmPmNormalization(unittest.TestCase):
+    """Regression tests for digit-anchored am/pm normalization.
+
+    Previously a global text.replace("am", "A M").replace("pm", "P M")
+    corrupted any ordinary word containing "am" or "pm", e.g. "am", "spam",
+    "program", "campus". The fix anchors the substitution to a preceding
+    digit so only actual time expressions are affected.
+    """
+
+    def test_am_word_untouched(self):
+        result = _normalize_dates_and_times("I am happy today", "en-US")
+        self.assertEqual(result, "I am happy today")
+
+    def test_spam_untouched(self):
+        result = _normalize_dates_and_times("this is spam", "en-US")
+        self.assertEqual(result, "this is spam")
+
+    def test_campus_program_untouched(self):
+        result = _normalize_dates_and_times("campus program schedule", "en-US")
+        self.assertEqual(result, "campus program schedule")
+
+    def test_am_radio_casing_untouched(self):
+        result = _normalize_dates_and_times("tune in to AM radio", "en-US")
+        self.assertEqual(result, "tune in to AM radio")
+
+    def test_combined_words_and_real_time(self):
+        result = _normalize_dates_and_times(
+            "I am happy this is spam, meet me at 9am", "en-US"
+        )
+        self.assertEqual(result, "I am happy this is spam, meet me at 9 A M")
+
+    def test_time_9am(self):
+        result = _normalize_dates_and_times("the train leaves at 9am", "en-US")
+        self.assertEqual(result, "the train leaves at 9 A M")
+
+    def test_time_with_space(self):
+        result = _normalize_dates_and_times("lunch is at 10 pm", "en-US")
+        self.assertEqual(result, "lunch is at 10 P M")
+
+    def test_time_uppercase(self):
+        result = _normalize_dates_and_times("wake up at 7AM sharp", "en-US")
+        self.assertEqual(result, "wake up at 7 A M sharp")
+
+    def test_time_dotted_pm(self):
+        result = _normalize_dates_and_times("arrive by 12p.m.", "en-US")
+        self.assertTrue(result.startswith("arrive by 12 P M"))
+
+    def test_multiple_times_in_one_sentence(self):
+        result = _normalize_dates_and_times(
+            "open from 9am to 5pm daily", "en-US"
+        )
+        self.assertEqual(result, "open from 9 A M to 5 P M daily")
+
+    def test_non_english_language_untouched(self):
+        # am/pm normalization is English-only; other languages must be
+        # unaffected even when the substrings "am"/"pm" appear.
+        text = "Je suis am spam et le programme est fantastique"
+        result = _normalize_dates_and_times(text, "fr-FR")
+        self.assertEqual(result, text)
+
+
+class TestMultiDateExpansion(unittest.TestCase):
+    """Regression tests for expanding every date in the text.
+
+    Previously date_pattern.search(text) only located and expanded the
+    FIRST date, leaving any subsequent dates in the text unspoken.
+    """
+
+    def test_single_date_expanded(self):
+        result = _normalize_dates_and_times(
+            "The event is on 12/25/2024", "en-US", "MDY"
+        )
+        self.assertNotIn("12/25/2024", result)
+        self.assertIn("december", result.lower())
+
+    def test_two_dates_both_expanded(self):
+        result = _normalize_dates_and_times(
+            "From 01/02/2025 until 03/04/2025", "en-US", "MDY"
+        )
+        self.assertNotIn("01/02/2025", result)
+        self.assertNotIn("03/04/2025", result)
+        self.assertIn("january", result.lower())
+        self.assertIn("march", result.lower())
+
+    def test_three_dates_all_expanded(self):
+        result = _normalize_dates_and_times(
+            "Dates: 01/02/2025, 03/04/2025 and 05/06/2025", "en-US", "MDY"
+        )
+        for raw_date in ("01/02/2025", "03/04/2025", "05/06/2025"):
+            self.assertNotIn(raw_date, result)
+
+    def test_identical_dates_both_expanded(self):
+        # Regression: the old implementation used text.replace(match, ...)
+        # which would replace ALL occurrences of an identical date string
+        # from a single match, but relied on search() to only ever find
+        # the first one. Confirm repeated identical dates are handled.
+        result = _normalize_dates_and_times(
+            "Reminder on 01/02/2025 and again 01/02/2025", "en-US", "MDY"
+        )
+        self.assertNotIn("01/02/2025", result)
+        self.assertEqual(result.lower().count("january"), 2)
+
+
+if __name__ == "__main__":
+    unittest.main()

text2spoken-0.0.2a1/tests/test_public_api.py

@@ -0,0 +1,50 @@
+"""The plain functions that a frontend composes around its own rules."""
+import unittest
+
+import text2spoken
+from text2spoken import (
+    expand_dates_and_times,
+    expand_hyphen_digits,
+    expand_units,
+    expand_word,
+    normalize,
+)
+
+
+class TestPublicFunctions(unittest.TestCase):
+
+    def test_all_names_resolve(self):
+        for name in text2spoken.__all__:
+            with self.subTest(name=name):
+                self.assertTrue(hasattr(text2spoken, name))
+
+    def test_version_is_the_version_module_value(self):
+        from text2spoken.version import __version__
+        self.assertEqual(text2spoken.__version__, __version__)
+
+    def test_expand_hyphen_digits_splits_a_word_from_a_digit(self):
+        self.assertEqual(expand_hyphen_digits("sub-23"), "sub 23")
+
+    def test_expand_hyphen_digits_keeps_a_range(self):
+        self.assertEqual(expand_hyphen_digits("3-2"), "3-2")
+
+    def test_expand_units_reads_the_portuguese_table(self):
+        self.assertEqual(expand_units("10kg", "pt"), "dez quilogramas")
+
+    def test_expand_dates_and_times_leaves_plain_words(self):
+        self.assertEqual(expand_dates_and_times("I am happy", "en"), "I am happy")
+
+    def test_expand_word_reads_a_contraction(self):
+        self.assertEqual(expand_word("can't", "en"), "can not")
+
+    def test_expand_word_reads_a_number_and_keeps_its_punctuation(self):
+        self.assertEqual(expand_word("23,", "en"), "twenty three,")
+
+    def test_expand_word_equals_the_word_pass_of_normalize(self):
+        for word in ("Dr.", "doesn't", "12", "3/4", "hello"):
+            with self.subTest(word=word):
+                self.assertEqual(expand_word(word, "en"), normalize(word, "en"))
+
+
+if __name__ == "__main__":
+    unittest.main()